講座名稱:Empowering Deep Modeling of 3D Point Clouds: From Representation, Learning Process, to Loss Function
講座人:Junhui Hou 副教授
講座時(shí)間:5月27日8:00-12:00
地點(diǎn):南校區(qū)會(huì)議中心101報(bào)告廳
講座人介紹:
代表性成果:
[1] Zhang Q, Hou J, Qian Y, et al. Flattening-net: Deep regular 2d representation for 3d point cloud analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
[2] Guo M, Hou J, Jin J, et al. Content-aware Warping for View Synthesis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
[3] Zhang Q, Hou J, Qian Y, et al. RegGeoNet: Learning Regular Representations for Large-Scale 3D Point Clouds[J]. International Journal of Computer Vision, 2022, 130(12): 3100-3122.
[4] Zhu Z, Hou J, Lyu X. Learning Graph-embedded Key-event Backtracing for Object Tracking in Event Clouds[J]. Advances in Neural Information Processing Systems, 2022, 35: 7462-7476.
[5] Liu H, Yuan H, Hou J, et al. PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling[J]. IEEE
Transactions on Image Processing, 2022, 31: 7389-7402.
主要成就:
在國(guó)際一流期刊和會(huì)議發(fā)表論文120余篇,指導(dǎo)培養(yǎng)博士研究生12余人。獲得政府資助研究基金超過(guò)1000萬(wàn)元。 2018年獲得香港研究資助局頒發(fā)的香港杰出青年學(xué)者(工程領(lǐng)域唯一獲獎(jiǎng)人)。 2020年獲得IEEE多媒體領(lǐng)域旗艦會(huì)議 IEEE ICME 杰出領(lǐng)域主席。獲得2022年斯坦福大學(xué)前2%高被引學(xué)者。
社會(huì)兼職:
擔(dān)任多媒體領(lǐng)域國(guó)際頂級(jí)期刊《IEEE Transactions on Image Processing》和《IEEE Transactions on Circuits and Systems for Video Technology》編委和多媒體領(lǐng)域國(guó)際頂級(jí)會(huì)議ACM MM 領(lǐng)域主席。
講座內(nèi)容:
非結(jié)構(gòu)化信號(hào)建模,視覺(jué)大模型應(yīng)用
主辦單位:人工智能學(xué)院